© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11536
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Is" followed by a descriptor

    np_acts-logits-general · gemini-2.0-flash

    organization descriptors and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antMatchers
    -0.70
    AddTagHelper
    -0.60
    EndContext
    -0.59
     occafion
    -0.54
     myſelf
    -0.54
    ividual
    -0.53
    WebElementEntity
    -0.53
    awtextra
    -0.53
    InSection
    -0.53
    ็จ
    -0.52
    POSITIVE LOGITS
     staffed
    0.86
     headquartered
    0.84
     run
    0.80
     committed
    0.76
     aware
    0.74
     proud
    0.72
     striving
    0.69
     located
    0.69
     operated
    0.68
     founded
    0.68
    Activations Density 0.315%

    No Known Activations